A computer-implemented method of configuring a communication network. Devices of the network are configured to communicate according to scheduling parameters that indicate a timing of transmitting and/or receiving data over the communication network. To configure the network, the method uses a configuration procedure that is customizable by a set of customization parameters. For a current scheduling instance, representing multiple data streams to be scheduled, the configuration procedure is applied to determine current scheduling parameters, which are provided to the respective devices. Concurrently with the current customization parameters being used, the customization parameters are optimized with respect to a performance indicator of scheduling the current scheduling instance according to the customization parameters, with the updated customization being used to determine scheduling parameters for future scheduling instances with improved performance with respect to the performance indicator.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein the applying of the configuration procedure includes applying a job scheduling algorithm to obtain a schedule for respective data transmissions corresponding to the multiple data streams, and deriving the scheduling parameters from the schedule.
3. The method of claim 2, wherein the applying of the job scheduling algorithm includes scheduling a data transmission from a first device to a current second device, and selecting a next second device for data transmission from the first device according to an ordering defined by the customization parameters.
6. The method of claim 5, wherein the customization parameters are binary values and the customization parameters are optimized by pseudo-Boolean optimization.
7. The method of claim 6, wherein the optimization comprises iteratively: training a scoring function to score candidate sets of customization parameters according to the performance indicator, and determining a further set of customization parameters by optimizing with respect to the trained scoring function.
10. The method of claim 9, wherein the applying of the change point detection procedure includes training a polyhedral classifier to distinguish between scheduling instances before and after the change point, and evaluating a performance of the trained classifier.
11. The method of claim 9, wherein the optimization is performed in response to a detected change point.
12. The method of claim 1, wherein the scheduling parameters represent a gate control list and/or data transmission timings for time-sensitive networking.
13. The method of claim 1, wherein the scoring function is a classifier.
15. The system of claim 14, wherein the system is a central network controller of a communication network, and wherein the scheduling parameters are for time-sensitive networking.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 3, 2023
December 10, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.